Ungulates conservation in the face of human development: Mining and roads' influences on habitat and connectivity in Iran's central plateau

Ecological Informatics, Год журнала: 2024, Номер 81, С. 102656 - 102656

Опубликована: Май 29, 2024

Язык: Английский

---

Efficient wildlife monitoring: Deep learning-based detection and counting of green turtles in coastal areas

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103009 - 103009

Опубликована: Янв. 1, 2025

Язык: Английский

---

Underwater bridge pier morphology measurement method via refraction correction and multi‐camera calibration

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2025, Номер unknown

Опубликована: Фев. 21, 2025

Abstract Underwater structural inspection is essential for ensuring the safety and longevity of bridges. To improve efficiency accuracy these inspections, this paper presents a method measuring morphology bridge piers through refraction correction multi‐camera calibration. Using an underwater visual platform with appropriate lighting, measurement equipment mitigates low visibility challenges. A coplanar camera parameter calibration based on encoded markers proposed to reduce effects refraction, along development multi‐refraction model. Additionally, novel extrinsic introduced stitch point clouds. comparative analysis two methods, conducted both in air underwater, has been performed validate approach. Finally, circular cross‐section shape pier was successfully measured, results defect localization were effectively presented.

Язык: Английский

---

A multi-target tracking method for UAV monitoring wildlife in Qinghai

PLoS ONE, Год журнала: 2025, Номер 20(4), С. e0317286 - e0317286

Опубликована: Апрель 11, 2025

The Procapra przewalskii, plays a vital role in sustaining the ecological balance within its habitat, yet it faces significant threats from environmental degradation and illegal poaching activities. In response to this urgent conservation need, article proposes multi-object tracking (MOT) method for unmanned aerial vehicle (UAV). Initially, approach utilizes modified YOLOv7 network, which incorporates Group-Selective Convolution (GSConv) Neck component, effectively enhancing network’s ability preserve detailed information while simultaneously reducing computational load. Subsequently, Content-Aware ReAssembly of Features (CARAFE), an innovative feature upscaling method, replaces conventional nearest neighbor interpolation minimize loss critical data during image processing. phase, Deep SORT algorithm is expanded with proprietary UAV camera motion compensation (CMC) module that eliminates impact jitters. Moreover, system has incorporated confidence optimization strategy (COS) enhances performance especially when individuals are partially or fully obscured. been tested on przewalskii shown be effective. results show gains metrics where achieved improvements 7.0% MOTA, 3.7% MOTP, 5.8% IDF1 score compared traditional model. Improved methods can alleviate occlusion rapid movement tracking, thereby more accurately monitoring status each protecting it. Also, efficiency multi-target through use sufficient operational demands UAV-based wildlife monitoring, thus being reliable tool accurate efficient desired.

Язык: Английский

---

Unmanned Aerial Vehicle Target Detection Integrating Computer Deep SORT Algorithm and Wireless Signal

International Journal of Interdisciplinary Telecommunications and Networking, Год журнала: 2025, Номер 17(1), С. 1 - 15

Опубликована: Апрель 19, 2025

With the advancement of unmanned aerial vehicle (UAV) technology, accurately detecting UAV targets has become increasingly challenging. This study addresses this issue by proposing a novel target detection method that integrates real-time tracking algorithms with wireless signal technology. Experimental results demonstrate each improved module positively contributes to overall method. Compared traditional object approaches, proposed achieves superior performance on both VisDrone and COCO datasets, precision, recall, F1 score, mean squared error values 96.07%, 95.84%, 96.33%, 0.023%, respectively. integrated approach effectively enhances accuracy detection, offering robust solution for positioning in applications.

Язык: Английский

---

LDDFSF-YOLO11: A Lightweight Insulator Defect Detection Method Focusing on Small-sized Features

IEEE Access, Год журнала: 2025, Номер 13, С. 90273 - 90292

Опубликована: Янв. 1, 2025

Язык: Английский

---

FocusTrack: multiple object tracking of unmanned aerial vehicle by associating interested semantic information

Опубликована: Окт. 22, 2024

Multiple Object Tracking (MOT) is a classical task in the field of computer vision, which aims to identify and track all objects video scene assign unique ID number each object. Tracking-by-Detection (TBD) paradigm has become mainstream framework for MOT due its high accuracy. With development UAV technology, research important military civilian value. However, it faces challenges such as class imbalance, many small targets, occlusion targets scene, makes difficult correctly match continuously targets. We propose new algorithm problem scenario. On one hand, solve imbalance dynamic adjustment parameter method based on gradient information training samples proposed improve generalization ability traditional loss function multi-class target tracking. other accuracy inter-frame matching, this paper introduces feature similarity calculation method, Wasserstein distance optimizes matching process according weight allocation mechanism importance. Finally, effectiveness verified VisDroneMOT2019 dataset. The results show that compared with existing algorithm, significant improvements tracking accuracy, trajectory integrity identity maintenance, achieving 38.8% MOTA 52.8% IDF1, are better than state-of-the-art algorithms.

Язык: Английский

---

Lightweight Sheep Counting Study Based on Mask R-CNN

Artificial Intelligence and Robotics Research, Год журнала: 2024, Номер 13(04), С. 920 - 929

Опубликована: Янв. 1, 2024

Язык: Английский

---